INDEX

Explanations

technical terms and symbols related to coding theory and error probability

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IonicModule

-0.61

UTERS

-0.54

 Lightboxes

-0.54

httphttps

-0.52

yakarta

-0.51

省市镇

-0.51

<()>

-0.51

 &___

-0.50

uslar

-0.50

 Alligator

-0.50

POSITIVE LOGITS

 channel

0.80

 symbol

0.75

 nahilalakip

0.74

 transmitter

0.70

 symbols

0.69

 Symbol

0.68

 receiver

0.68

 Channel

0.68

 fading

0.67

channel

0.66

Activations Density 0.924%

technical terms and symbols related to coding theory and error probability

No Comments

No Known Activations